© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58820
    Prev
    Next
    INDEX
    Explanations

    installation has been

    np_acts-logits-general · gemini-2.5-flash-lite

    affects the, implications of, varies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ập
    0.55
    iled
    0.50
    iz
    0.48
    2
    0.47
    Beer
    0.46
     설명
    0.46
    वे
    0.45
    roqu
    0.44
    ２
    0.44
    TYPE
    0.43
    POSITIVE LOGITS
     insignia
    0.57
     occupant
    0.54
    គ្មាន
    0.47
     როგორც
    0.46
     leakage
    0.46
     kaliteli
    0.45
     yolk
    0.44
    <unused662>
    0.44
     gemstones
    0.44
     আবদুল্লাহ
    0.44
    Activations Density 0.000%

    No Known Activations